EPS Dashboard

Authors: Jared Glover

Summary

The authors built a simple memory system for language models that stores not just facts but emotional responses. They identify emotion features in a small Gemma model using sparse autoencoders (tools that decompose model activations into interpretable components), save emotion vectors during an experience, then re-inject part of that emotion signal when the model later recalls similar contexts. Testing on decision tasks, they find that emotion alone improves threat detection but doesn't improve choices; semantic labels (plain facts) alone get 52% correct decisions, but semantic + emotion together hits 80%—replicating the neuroscience finding that emotion amplifies knowledge into action rather than replacing it.

Main takeaways:

Sparse autoencoders on layer 22 of Gemma 3 1B picked out 310 emotion-specific features with psychologically meaningful structure
Re-injecting emotion vectors at recall (triggered by context similarity at layer 7) steepens the model's threat-safety gradient compared to no memory
Emotion echo alone doesn't help decision accuracy; semantic memory alone gets 52% good choices; combining both pushes accuracy to 80%
The result mirrors Damasio's somatic marker hypothesis: emotion marks help only when paired with factual knowledge
Demonstrates a concrete technique for conditioning model behavior on past emotional context, not just facts

Relevance

Directly relevant to my work on behavioral installation and persona mechanisms. This paper shows emotion vectors—extracted via SAEs and re-injected at specific layers—can condition model behavior, which is conceptually similar to my activation steering and fine-tuning work. The context-triggered re-injection at layer 7 is a concrete implementation of conditional behavior that could inform how persona markers or steering vectors are applied.

Abstract

arXiv:2605.08611v1 Announce Type: new Abstract: Current language model memory systems store what happened but not how it felt. This distinction -- between semantic memory (knowing about a past event) and episodic memory (re-experiencing it) -- was identified by Tulving as the difference between noetic and autonoetic consciousness. Damasio demonstrated that humans with intact knowledge but absent emotional markers exhibit impaired decision-making. We bridge this gap for language models. Using Gemma 3 1B-IT with pretrained Gemma Scope 2 sparse autoencoders, we identify 310 emotion-exclusive features at layer 22 with psychologically valid geometry. We construct distinctive-feature emotion vectors during experience and partially re-inject them during recall, triggered by context similarity at layer 7. We test four conditions paralleling Damasio's framework: A (no memory), B (semantic labels), C (emotion echo), and BC (semantic + echo). For emotional orientation, the echo alone steepens the threat-safety gradient: the regression slope of threat rating on contextual similarity is 0.80 for C vs 0.56 for A ($p$=0.011, permutation test). For decisions, the echo amplifies knowledge into action: BC=80% good choices vs B=52% ($z$=+2.60, $p$<0.01), while the echo alone has no effect (C=22%, n.s.). The echo changes how the model feels independently, but changes what it does only when combined with knowledge -- replicating Damasio's core finding. The echo amplifies knowledge. It does not replace it.